Speaker
Andrew, on behalf of the GraphCast team and GenCast team from Google DeepMind El-Kadi
(Google DeepMind)
Description
The recent emergence of quality data, large scale compute and deep learning advancements has enabled an acceleration in the field of Machine Learning for Weather Forecasting. Today's talk centers on two pieces of work: GraphCast and GenCast, both Medium Range Global Weather Forecasting models. The former produces deterministic forecasts up to 10 days into the future, while the latter makes probabilistic forecasts, up to 15 days into the future. We cover: their state of the art results compared to the most accurate operational equivalents, explore subtle aspects of their training data heterogeneity and discuss the role they play as we move towards larger weather models.
| Contribution length | Long |
|---|
Authors
Alexander Merose
(Google DeepMind)
Alexander Pritzel
(Google DeepMind)
Alvaro Sanchez-Gonzalez
(Google DeepMind)
Andrew El-Kadi
(Google DeepMind)
Dominic Masters
(Google DeepMind)
Ferran Alet
(Google DeepMind)
George Holland
(Google DeepMind)
Ilan Price
(Google DeepMind)
Jacklynn Stott
(Google DeepMind)
Matthew Willson
(Google DeepMind)
Meire Fortunato
(Google DeepMind)
Oriol Vinyals
(Google DeepMind)
Peter Battaglia
(Google DeepMind)
Peter Wirnsberger
(Google DeepMind)
Remi Lam
(Google DeepMind)
Shakir Mohamed
(Google DeepMind)
Stephan Hoyer
(Google DeepMind)
Suman Ravuri
(Google DeepMind)
Timo Ewalds
(Google DeepMind)
Tom Andersson
(Google DeepMind)
Weihua Hu
(Google DeepMind)
Zach Eaton-Rosen
